File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Parallel Algorithms for Perceptual Grouping on Distributed Memory Machines

TitleParallel Algorithms for Perceptual Grouping on Distributed Memory Machines
Authors
Issue Date1998
PublisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/jpdc
Citation
Journal Of Parallel And Distributed Computing, 1998, v. 50 n. 1-2, p. 123-143 How to Cite?
AbstractPerceptual grouping is a key intermediate-level vision problem. Parallel solutions to this problem are characterized by uneven distribution of symbolic features among the processors, unbalanced workload, and irregular interprocessor data dependency caused by the input image. In this paper, we propose two load-balancing techniques for parallelizing perceptual grouping on distributed-memory machines. By using an initial workload estimate, we first partition the computations to distribute the workload across the processors. In addition, we asynchronously perform ongoing task migrations to adapt to the unbalanced workload which may evolve differently from the initial estimate. We also discuss two strategies to manage the irregular interprocessor data dependency. To illustrate our ideas, perceptual grouping steps used in an integrated vision system for building detection are used as examples. Our experimental results show that, given 8K extracted line segments from a 1K × 1K image, both the line and junction grouping steps can be completed in 0.644 s on a 32-node SP2 and in 0.585 s on a 32-node T3D. For the same grouping steps, a serial implementation requires 10.550 s and 10.023 s on a single node of SP2 and T3D, respectively. The implementations were performed using the message passing interface standard and are portable to other high performance computing platforms. © 1998 Academic Press.
Persistent Identifierhttp://hdl.handle.net/10722/89113
ISSN
2023 Impact Factor: 3.4
2023 SCImago Journal Rankings: 1.187
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorChung, Yen_HK
dc.contributor.authorWang, CLen_HK
dc.contributor.authorPrasanna, VKen_HK
dc.date.accessioned2010-09-06T09:52:33Z-
dc.date.available2010-09-06T09:52:33Z-
dc.date.issued1998en_HK
dc.identifier.citationJournal Of Parallel And Distributed Computing, 1998, v. 50 n. 1-2, p. 123-143en_HK
dc.identifier.issn0743-7315en_HK
dc.identifier.urihttp://hdl.handle.net/10722/89113-
dc.description.abstractPerceptual grouping is a key intermediate-level vision problem. Parallel solutions to this problem are characterized by uneven distribution of symbolic features among the processors, unbalanced workload, and irregular interprocessor data dependency caused by the input image. In this paper, we propose two load-balancing techniques for parallelizing perceptual grouping on distributed-memory machines. By using an initial workload estimate, we first partition the computations to distribute the workload across the processors. In addition, we asynchronously perform ongoing task migrations to adapt to the unbalanced workload which may evolve differently from the initial estimate. We also discuss two strategies to manage the irregular interprocessor data dependency. To illustrate our ideas, perceptual grouping steps used in an integrated vision system for building detection are used as examples. Our experimental results show that, given 8K extracted line segments from a 1K × 1K image, both the line and junction grouping steps can be completed in 0.644 s on a 32-node SP2 and in 0.585 s on a 32-node T3D. For the same grouping steps, a serial implementation requires 10.550 s and 10.023 s on a single node of SP2 and T3D, respectively. The implementations were performed using the message passing interface standard and are portable to other high performance computing platforms. © 1998 Academic Press.en_HK
dc.languageengen_HK
dc.publisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/jpdcen_HK
dc.relation.ispartofJournal of Parallel and Distributed Computingen_HK
dc.titleParallel Algorithms for Perceptual Grouping on Distributed Memory Machinesen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0743-7315&volume=50&spage=123&epage=143&date=1998&atitle=Parallel+Algorithms+for+Perceptual+Grouping+on+Distributed+Memory+Machinesen_HK
dc.identifier.emailWang, CL:clwang@cs.hku.hken_HK
dc.identifier.authorityWang, CL=rp00183en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1006/jpdc.1998.1438en_HK
dc.identifier.scopuseid_2-s2.0-0040091783en_HK
dc.identifier.hkuros33656en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0040091783&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume50en_HK
dc.identifier.issue1-2en_HK
dc.identifier.spage123en_HK
dc.identifier.epage143en_HK
dc.identifier.isiWOS:000074067400007-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridChung, Y=7404387981en_HK
dc.identifier.scopusauthoridWang, CL=7501646188en_HK
dc.identifier.scopusauthoridPrasanna, VK=7005057102en_HK
dc.identifier.issnl0743-7315-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats